Inception Modules Enhance Brain Tumor Segmentation
Inception Modules Enhance Brain Tumor Segmentation
复制标题
DOI：
10.3389/fncom.2019.00044
复制
发表时间：
2019-07-12
影响因子：
3.2
通讯作者：
Fathallah-Shaykh, Hassan M.
中科院分区：
文献类型：
--
作者：
Cahall, Daniel E.;Rasool, Ghulam;Fathallah-Shaykh, Hassan M.
脑肿瘤的磁共振成像通常用于神经肿瘤学诊所的诊断、治疗计划和治疗后肿瘤监测。目前，医生花费大量时间手动描绘大脑的不同结构。空间和结构的变化，以及强度不均匀性的图像，使计算机辅助分割的问题非常具有挑战性。我们提出了一种新的肿瘤描绘图像分割框架，该框架受益于计算机视觉中两种最先进的机器学习架构，即，Inception模块和U-Net图像分割架构。此外，我们的框架包括两个学习制度，即，学习分割肿瘤内结构（坏死和非增强肿瘤核心、瘤周水肿和增强肿瘤）或学习分割神经胶质瘤亚区域（整个肿瘤、肿瘤核心和增强肿瘤）。这些学习制度被纳入一个新提出的损失函数，这是基于骰子相似系数（DSC）。在我们的实验中，我们量化了在U-Net架构中引入Inception模块的影响，以及将学习算法的目标函数从肿瘤内结构分割到胶质瘤子区域。我们发现，结合Inception模块显著提高了所有胶质瘤子区域的分割性能（p < 0.001）。此外，在具有Inception模块的架构中，以分割肿瘤内结构的学习目标训练的模型优于以分割整个肿瘤的胶质瘤子区域为目标训练的模型（p < 0.001）。改进的性能与新引入的Inception模块提取的多尺度特征和基于DSC的修改后的损失函数有关。
Magnetic resonance images of brain tumors are routinely used in neuro-oncology clinics for diagnosis, treatment planning, and post-treatment tumor surveillance. Currently, physicians spend considerable time manually delineating different structures of the brain. Spatial and structural variations, as well as intensity inhomogeneity across images, make the problem of computer-assisted segmentation very challenging. We propose a new image segmentation framework for tumor delineation that benefits from two state-of-the-art machine learning architectures in computer vision, i.e., Inception modules and U-Net image segmentation architecture. Furthermore, our framework includes two learning regimes, i.e., learning to segment intra-tumoral structures (necrotic and non-enhancing tumor core, peritumoral edema, and enhancing tumor) or learning to segment glioma sub-regions (whole tumor, tumor core, and enhancing tumor). These learning regimes are incorporated into a newly proposed loss function which is based on the Dice similarity coefficient (DSC). In our experiments, we quantified the impact of introducing the Inception modules in the U-Net architecture, as well as, changing the objective function for the learning algorithm from segmenting the intra-tumoral structures to glioma sub-regions. We found that incorporating Inception modules significantly improved the segmentation performance (p < 0.001) for all glioma sub-regions. Moreover, in architectures with Inception modules, the models trained with the learning objective of segmenting the intra-tumoral structures outperformed the models trained with the objective of segmenting the glioma sub-regions for the whole tumor (p < 0.001). The improved performance is linked to multiscale features extracted by newly introduced Inception module and the modified loss function based on the DSC.